mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-10-22 17:11:27 +02:00
Compare commits
7 Commits
55cb7c5ec9
...
b34d50738a
Author | SHA1 | Date | |
---|---|---|---|
|
b34d50738a | ||
|
46fe60ff19 | ||
|
0b7ec08816 | ||
|
40054cb4a7 | ||
|
fed53d70bd | ||
|
ec2f4bf082 | ||
|
637ccf3523 |
|
@ -33,21 +33,21 @@ class AfreecaTVBaseIE(InfoExtractor):
|
||||||
}
|
}
|
||||||
|
|
||||||
response = self._download_json(
|
response = self._download_json(
|
||||||
'https://login.afreecatv.com/app/LoginAction.php', None,
|
'https://login.sooplive.co.kr/app/LoginAction.php', None,
|
||||||
'Logging in', data=urlencode_postdata(login_form))
|
'Logging in', data=urlencode_postdata(login_form))
|
||||||
|
|
||||||
_ERRORS = {
|
_ERRORS = {
|
||||||
-4: 'Your account has been suspended due to a violation of our terms and policies.',
|
-4: 'Your account has been suspended due to a violation of our terms and policies.',
|
||||||
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
|
-5: 'https://member.sooplive.co.kr/app/user_delete_progress.php',
|
||||||
-6: 'https://login.afreecatv.com/membership/changeMember.php',
|
-6: 'https://login.sooplive.co.kr/membership/changeMember.php',
|
||||||
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
|
-8: "Hello! Soop here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
|
||||||
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
|
-9: 'https://member.sooplive.co.kr/app/pop_login_block.php',
|
||||||
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
|
-11: 'https://login.sooplive.co.kr/afreeca/second_login.php',
|
||||||
-12: 'https://member.afreecatv.com/app/user_security.php',
|
-12: 'https://member.sooplive.co.kr/app/user_security.php',
|
||||||
0: 'The username does not exist or you have entered the wrong password.',
|
0: 'The username does not exist or you have entered the wrong password.',
|
||||||
-1: 'The username does not exist or you have entered the wrong password.',
|
-1: 'The username does not exist or you have entered the wrong password.',
|
||||||
-3: 'You have entered your username/password incorrectly.',
|
-3: 'You have entered your username/password incorrectly.',
|
||||||
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
|
-7: 'You cannot use your Global Soop account to access Korean Soop.',
|
||||||
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
|
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
|
||||||
-32008: 'You have failed to log in. Please contact our Help Center.',
|
-32008: 'You have failed to log in. Please contact our Help Center.',
|
||||||
}
|
}
|
||||||
|
@ -61,76 +61,40 @@ class AfreecaTVBaseIE(InfoExtractor):
|
||||||
|
|
||||||
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
|
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
|
||||||
return self._download_json(Request(
|
return self._download_json(Request(
|
||||||
f'https://api.m.afreecatv.com/{endpoint}',
|
f'https://api.m.sooplive.co.kr/{endpoint}',
|
||||||
data=data, headers=headers, query=query,
|
data=data, headers=headers, query=query,
|
||||||
extensions={'legacy_ssl': True}), display_id,
|
extensions={'legacy_ssl': True}), display_id,
|
||||||
'Downloading API JSON', 'Unable to download API JSON')
|
'Downloading API JSON', 'Unable to download API JSON')
|
||||||
|
|
||||||
|
|
||||||
class AfreecaTVIE(AfreecaTVBaseIE):
|
class AfreecaTVIE(AfreecaTVBaseIE):
|
||||||
IE_NAME = 'afreecatv'
|
IE_NAME = 'soop'
|
||||||
IE_DESC = 'afreecatv.com'
|
IE_DESC = 'sooplive.co.kr'
|
||||||
_VALID_URL = r'''(?x)
|
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/(?:PLAYER/STATION|player)/(?P<id>\d+)/?(?:$|[?#&])'
|
||||||
https?://
|
|
||||||
(?:
|
|
||||||
(?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)?
|
|
||||||
(?:
|
|
||||||
/app/(?:index|read_ucc_bbs)\.cgi|
|
|
||||||
/player/[Pp]layer\.(?:swf|html)
|
|
||||||
)\?.*?\bnTitleNo=|
|
|
||||||
vod\.afreecatv\.com/(PLAYER/STATION|player)/
|
|
||||||
)
|
|
||||||
(?P<id>\d+)/?(?:$|[?#&])
|
|
||||||
'''
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
|
'url': 'https://vod.sooplive.co.kr/player/96753363',
|
||||||
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '36164052',
|
'id': '20230108_9FF5BEE1_244432674_1',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '데일리 에이프릴 요정들의 시상식!',
|
'uploader_id': 'rlantnghks',
|
||||||
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
|
'uploader': '페이즈으',
|
||||||
'uploader': 'dailyapril',
|
'duration': 10840,
|
||||||
'uploader_id': 'dailyapril',
|
'thumbnail': r're:https?://videoimg\.sooplive\.co/.kr/.+',
|
||||||
'upload_date': '20160503',
|
'upload_date': '20230108',
|
||||||
|
'timestamp': 1673218805,
|
||||||
|
'title': '젠지 페이즈',
|
||||||
},
|
},
|
||||||
'skip': 'Video is gone',
|
'params': {
|
||||||
}, {
|
'skip_download': True,
|
||||||
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '36153164',
|
|
||||||
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
|
|
||||||
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
|
|
||||||
'uploader': 'dailyapril',
|
|
||||||
'uploader_id': 'dailyapril',
|
|
||||||
},
|
},
|
||||||
'playlist_count': 2,
|
|
||||||
'playlist': [{
|
|
||||||
'md5': 'd8b7c174568da61d774ef0203159bf97',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '36153164_1',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
|
|
||||||
'upload_date': '20160502',
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '36153164_2',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
|
|
||||||
'upload_date': '20160502',
|
|
||||||
},
|
|
||||||
}],
|
|
||||||
'skip': 'Video is gone',
|
|
||||||
}, {
|
}, {
|
||||||
# non standard key
|
# non standard key
|
||||||
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
|
'url': 'http://vod.sooplive.co.kr/PLAYER/STATION/20515605',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '20170411_BE689A0E_190960999_1_2_h',
|
'id': '20170411_BE689A0E_190960999_1_2_h',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '혼자사는여자집',
|
'title': '혼자사는여자집',
|
||||||
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
|
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
|
||||||
'uploader': '♥이슬이',
|
'uploader': '♥이슬이',
|
||||||
'uploader_id': 'dasl8121',
|
'uploader_id': 'dasl8121',
|
||||||
'upload_date': '20170411',
|
'upload_date': '20170411',
|
||||||
|
@ -142,12 +106,12 @@ class AfreecaTVIE(AfreecaTVBaseIE):
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
# adult content
|
# adult content
|
||||||
'url': 'https://vod.afreecatv.com/player/97267690',
|
'url': 'https://vod.sooplive.co.kr/player/97267690',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '20180327_27901457_202289533_1',
|
'id': '20180327_27901457_202289533_1',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '[생]빨개요♥ (part 1)',
|
'title': '[생]빨개요♥ (part 1)',
|
||||||
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
|
'thumbnail': r're:https?://(?:video|st)img\.sooplive\.co\.kr/.+',
|
||||||
'uploader': '[SA]서아',
|
'uploader': '[SA]서아',
|
||||||
'uploader_id': 'bjdyrksu',
|
'uploader_id': 'bjdyrksu',
|
||||||
'upload_date': '20180327',
|
'upload_date': '20180327',
|
||||||
|
@ -157,36 +121,17 @@ class AfreecaTVIE(AfreecaTVBaseIE):
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
'skip': 'The VOD does not exist',
|
'skip': 'The VOD does not exist',
|
||||||
}, {
|
|
||||||
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://vod.afreecatv.com/player/96753363',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '20230108_9FF5BEE1_244432674_1',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'uploader_id': 'rlantnghks',
|
|
||||||
'uploader': '페이즈으',
|
|
||||||
'duration': 10840,
|
|
||||||
'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
|
|
||||||
'upload_date': '20230108',
|
|
||||||
'timestamp': 1673218805,
|
|
||||||
'title': '젠지 페이즈',
|
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
|
||||||
}, {
|
}, {
|
||||||
# adult content
|
# adult content
|
||||||
'url': 'https://vod.afreecatv.com/player/70395877',
|
'url': 'https://vod.sooplive.co.kr/player/70395877',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
# subscribers only
|
# subscribers only
|
||||||
'url': 'https://vod.afreecatv.com/player/104647403',
|
'url': 'https://vod.sooplive.co.kr/player/104647403',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
# private
|
# private
|
||||||
'url': 'https://vod.afreecatv.com/player/81669846',
|
'url': 'https://vod.sooplive.co.kr/player/81669846',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
@ -262,11 +207,11 @@ class AfreecaTVIE(AfreecaTVBaseIE):
|
||||||
|
|
||||||
|
|
||||||
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
|
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
|
||||||
IE_NAME = 'afreecatv:catchstory'
|
IE_NAME = 'soop:catchstory'
|
||||||
IE_DESC = 'afreecatv.com catch story'
|
IE_DESC = 'sooplive.co.kr catch story'
|
||||||
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
|
_VALID_URL = r'https?://vod\.(?:sooplive\.co\.kr|afreecatv\.com)/player/(?P<id>\d+)/catchstory'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://vod.afreecatv.com/player/103247/catchstory',
|
'url': 'https://vod.sooplive.co.kr/player/103247/catchstory',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '103247',
|
'id': '103247',
|
||||||
},
|
},
|
||||||
|
@ -299,11 +244,11 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
|
||||||
|
|
||||||
|
|
||||||
class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
IE_NAME = 'afreecatv:live'
|
IE_NAME = 'soop:live'
|
||||||
IE_DESC = 'afreecatv.com livestreams'
|
IE_DESC = 'sooplive.co.kr livestreams'
|
||||||
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
|
_VALID_URL = r'https?://play\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)(?:/(?P<bno>\d+))?'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://play.afreecatv.com/pyh3646/237852185',
|
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '237852185',
|
'id': '237852185',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
|
@ -315,30 +260,30 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
},
|
},
|
||||||
'skip': 'Livestream has ended',
|
'skip': 'Livestream has ended',
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://play.afreecatv.com/pyh3646/237852185',
|
'url': 'https://play.sooplive.co.kr/pyh3646/237852185',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://play.afreecatv.com/pyh3646',
|
'url': 'https://play.sooplive.co.kr/pyh3646',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
|
_LIVE_API_URL = 'https://live.sooplive.co.kr/afreeca/player_live_api.php'
|
||||||
_WORKING_CDNS = [
|
_WORKING_CDNS = [
|
||||||
'gcp_cdn', # live-global-cdn-v02.afreecatv.com
|
'gcp_cdn', # live-global-cdn-v02.sooplive.co.kr
|
||||||
'gs_cdn_pc_app', # pc-app.stream.afreecatv.com
|
'gs_cdn_pc_app', # pc-app.stream.sooplive.co.kr
|
||||||
'gs_cdn_mobile_web', # mobile-web.stream.afreecatv.com
|
'gs_cdn_mobile_web', # mobile-web.stream.sooplive.co.kr
|
||||||
'gs_cdn_pc_web', # pc-web.stream.afreecatv.com
|
'gs_cdn_pc_web', # pc-web.stream.sooplive.co.kr
|
||||||
]
|
]
|
||||||
_BAD_CDNS = [
|
_BAD_CDNS = [
|
||||||
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
|
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
|
||||||
'gs_cdn_chromecast', # chromecast.stream.afreecatv.com (HTTP Error 400)
|
'gs_cdn_chromecast', # chromecast.stream.sooplive.co.kr (HTTP Error 400)
|
||||||
'azure_cdn', # live-global-cdn-v01.afreecatv.com (cannot resolve)
|
'azure_cdn', # live-global-cdn-v01.sooplive.co.kr (cannot resolve)
|
||||||
'aws_cf', # live-global-cdn-v03.afreecatv.com (cannot resolve)
|
'aws_cf', # live-global-cdn-v03.sooplive.co.kr (cannot resolve)
|
||||||
'kt_cdn', # kt.stream.afreecatv.com (HTTP Error 400)
|
'kt_cdn', # kt.stream.sooplive.co.kr (HTTP Error 400)
|
||||||
]
|
]
|
||||||
|
|
||||||
def _extract_formats(self, channel_info, broadcast_no, aid):
|
def _extract_formats(self, channel_info, broadcast_no, aid):
|
||||||
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
|
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.sooplive.co.kr'
|
||||||
|
|
||||||
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
|
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
|
||||||
default_cdn_ids = orderedSet([
|
default_cdn_ids = orderedSet([
|
||||||
|
@ -358,7 +303,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
try:
|
try:
|
||||||
return self._extract_m3u8_formats(
|
return self._extract_m3u8_formats(
|
||||||
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
|
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
|
||||||
headers={'Referer': 'https://play.afreecatv.com/'})
|
headers={'Referer': 'https://play.sooplive.co.kr/'})
|
||||||
except ExtractorError as e:
|
except ExtractorError as e:
|
||||||
if attempt == len(cdn_ids):
|
if attempt == len(cdn_ids):
|
||||||
raise
|
raise
|
||||||
|
@ -374,7 +319,13 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
broadcaster_id = channel_info.get('BJID') or broadcaster_id
|
broadcaster_id = channel_info.get('BJID') or broadcaster_id
|
||||||
broadcast_no = channel_info.get('BNO') or broadcast_no
|
broadcast_no = channel_info.get('BNO') or broadcast_no
|
||||||
if not broadcast_no:
|
if not broadcast_no:
|
||||||
raise UserNotLive(video_id=broadcaster_id)
|
result = channel_info.get('RESULT')
|
||||||
|
if result == 0:
|
||||||
|
raise UserNotLive(video_id=broadcaster_id)
|
||||||
|
elif result == -6:
|
||||||
|
self.raise_login_required(
|
||||||
|
'This channel is streaming for subscribers only', method='password')
|
||||||
|
raise ExtractorError('Unable to extract broadcast number')
|
||||||
|
|
||||||
password = self.get_param('videopassword')
|
password = self.get_param('videopassword')
|
||||||
if channel_info.get('BPWD') == 'Y' and password is None:
|
if channel_info.get('BPWD') == 'Y' and password is None:
|
||||||
|
@ -403,7 +354,7 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
formats = self._extract_formats(channel_info, broadcast_no, aid)
|
formats = self._extract_formats(channel_info, broadcast_no, aid)
|
||||||
|
|
||||||
station_info = traverse_obj(self._download_json(
|
station_info = traverse_obj(self._download_json(
|
||||||
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
|
'https://st.sooplive.co.kr/api/get_station_status.php', broadcast_no,
|
||||||
'Downloading channel metadata', 'Unable to download channel metadata',
|
'Downloading channel metadata', 'Unable to download channel metadata',
|
||||||
query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
|
query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
|
||||||
|
|
||||||
|
@ -419,11 +370,11 @@ class AfreecaTVLiveIE(AfreecaTVBaseIE):
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
class AfreecaTVUserIE(InfoExtractor):
|
class AfreecaTVUserIE(AfreecaTVBaseIE):
|
||||||
IE_NAME = 'afreecatv:user'
|
IE_NAME = 'soop:user'
|
||||||
_VALID_URL = r'https?://bj\.afreeca(?:tv)?\.com/(?P<id>[^/]+)/vods/?(?P<slug_type>[^/]+)?'
|
_VALID_URL = r'https?://ch\.(?:sooplive\.co\.kr|afreecatv\.com)/(?P<id>[^/?#]+)/vods/?(?P<slug_type>[^/?#]+)?'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods/review',
|
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/review',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'_type': 'playlist',
|
'_type': 'playlist',
|
||||||
'id': 'ryuryu24',
|
'id': 'ryuryu24',
|
||||||
|
@ -431,7 +382,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||||
},
|
},
|
||||||
'playlist_count': 218,
|
'playlist_count': 218,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://bj.afreecatv.com/parang1995/vods/highlight',
|
'url': 'https://ch.sooplive.co.kr/parang1995/vods/highlight',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'_type': 'playlist',
|
'_type': 'playlist',
|
||||||
'id': 'parang1995',
|
'id': 'parang1995',
|
||||||
|
@ -439,7 +390,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||||
},
|
},
|
||||||
'playlist_count': 997,
|
'playlist_count': 997,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods',
|
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'_type': 'playlist',
|
'_type': 'playlist',
|
||||||
'id': 'ryuryu24',
|
'id': 'ryuryu24',
|
||||||
|
@ -447,7 +398,7 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||||
},
|
},
|
||||||
'playlist_count': 221,
|
'playlist_count': 221,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://bj.afreecatv.com/ryuryu24/vods/balloonclip',
|
'url': 'https://ch.sooplive.co.kr/ryuryu24/vods/balloonclip',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'_type': 'playlist',
|
'_type': 'playlist',
|
||||||
'id': 'ryuryu24',
|
'id': 'ryuryu24',
|
||||||
|
@ -459,12 +410,12 @@ class AfreecaTVUserIE(InfoExtractor):
|
||||||
|
|
||||||
def _fetch_page(self, user_id, user_type, page):
|
def _fetch_page(self, user_id, user_type, page):
|
||||||
page += 1
|
page += 1
|
||||||
info = self._download_json(f'https://bjapi.afreecatv.com/api/{user_id}/vods/{user_type}', user_id,
|
info = self._download_json(f'https://chapi.sooplive.co.kr/api/{user_id}/vods/{user_type}', user_id,
|
||||||
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
|
query={'page': page, 'per_page': self._PER_PAGE, 'orderby': 'reg_date'},
|
||||||
note=f'Downloading {user_type} video page {page}')
|
note=f'Downloading {user_type} video page {page}')
|
||||||
for item in info['data']:
|
for item in info['data']:
|
||||||
yield self.url_result(
|
yield self.url_result(
|
||||||
f'https://vod.afreecatv.com/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
|
f'https://vod.sooplive.co.kr/player/{item["title_no"]}/', AfreecaTVIE, item['title_no'])
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
|
user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')
|
||||||
|
|
|
@ -4,7 +4,6 @@ import json
|
||||||
import re
|
import re
|
||||||
import time
|
import time
|
||||||
import urllib.parse
|
import urllib.parse
|
||||||
import xml.etree.ElementTree
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..networking import HEADRequest
|
from ..networking import HEADRequest
|
||||||
|
@ -12,7 +11,6 @@ from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
float_or_none,
|
float_or_none,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
join_nonempty,
|
|
||||||
js_to_json,
|
js_to_json,
|
||||||
mimetype2ext,
|
mimetype2ext,
|
||||||
orderedSet,
|
orderedSet,
|
||||||
|
@ -524,14 +522,13 @@ class CBCGemIE(InfoExtractor):
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
# This is a normal, public, TV show video
|
# This is a normal, public, TV show video
|
||||||
'url': 'https://gem.cbc.ca/media/schitts-creek/s06e01',
|
'url': 'https://gem.cbc.ca/media/schitts-creek/s06e01',
|
||||||
'md5': '93dbb31c74a8e45b378cf13bd3f6f11e',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'schitts-creek/s06e01',
|
'id': 'schitts-creek/s06e01',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Smoke Signals',
|
'title': 'Smoke Signals',
|
||||||
'description': 'md5:929868d20021c924020641769eb3e7f1',
|
'description': 'md5:929868d20021c924020641769eb3e7f1',
|
||||||
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/episode/perso/cbc_schitts_creek_season_06e01_thumbnail_v01.jpg?im=Resize=(Size)',
|
'thumbnail': r're:https://images\.radio-canada\.ca/[^#?]+/cbc_schitts_creek_season_06e01_thumbnail_v01\.jpg',
|
||||||
'duration': 1314,
|
'duration': 1324,
|
||||||
'categories': ['comedy'],
|
'categories': ['comedy'],
|
||||||
'series': 'Schitt\'s Creek',
|
'series': 'Schitt\'s Creek',
|
||||||
'season': 'Season 6',
|
'season': 'Season 6',
|
||||||
|
@ -539,19 +536,21 @@ class CBCGemIE(InfoExtractor):
|
||||||
'episode': 'Smoke Signals',
|
'episode': 'Smoke Signals',
|
||||||
'episode_number': 1,
|
'episode_number': 1,
|
||||||
'episode_id': 'schitts-creek/s06e01',
|
'episode_id': 'schitts-creek/s06e01',
|
||||||
|
'upload_date': '20210618',
|
||||||
|
'timestamp': 1623988800,
|
||||||
|
'release_date': '20200107',
|
||||||
|
'release_timestamp': 1578427200,
|
||||||
},
|
},
|
||||||
'params': {'format': 'bv'},
|
'params': {'format': 'bv'},
|
||||||
'skip': 'Geo-restricted to Canada',
|
|
||||||
}, {
|
}, {
|
||||||
# This video requires an account in the browser, but works fine in yt-dlp
|
# This video requires an account in the browser, but works fine in yt-dlp
|
||||||
'url': 'https://gem.cbc.ca/media/schitts-creek/s01e01',
|
'url': 'https://gem.cbc.ca/media/schitts-creek/s01e01',
|
||||||
'md5': '297a9600f554f2258aed01514226a697',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'schitts-creek/s01e01',
|
'id': 'schitts-creek/s01e01',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'The Cup Runneth Over',
|
'title': 'The Cup Runneth Over',
|
||||||
'description': 'md5:9bca14ea49ab808097530eb05a29e797',
|
'description': 'md5:9bca14ea49ab808097530eb05a29e797',
|
||||||
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/episode/perso/cbc_schitts_creek_season_01e01_thumbnail_v01.jpg?im=Resize=(Size)',
|
'thumbnail': r're:https://images\.radio-canada\.ca/[^#?]+/cbc_schitts_creek_season_01e01_thumbnail_v01\.jpg',
|
||||||
'series': 'Schitt\'s Creek',
|
'series': 'Schitt\'s Creek',
|
||||||
'season_number': 1,
|
'season_number': 1,
|
||||||
'season': 'Season 1',
|
'season': 'Season 1',
|
||||||
|
@ -560,9 +559,12 @@ class CBCGemIE(InfoExtractor):
|
||||||
'episode_id': 'schitts-creek/s01e01',
|
'episode_id': 'schitts-creek/s01e01',
|
||||||
'duration': 1309,
|
'duration': 1309,
|
||||||
'categories': ['comedy'],
|
'categories': ['comedy'],
|
||||||
|
'upload_date': '20210617',
|
||||||
|
'timestamp': 1623902400,
|
||||||
|
'release_date': '20151124',
|
||||||
|
'release_timestamp': 1448323200,
|
||||||
},
|
},
|
||||||
'params': {'format': 'bv'},
|
'params': {'format': 'bv'},
|
||||||
'skip': 'Geo-restricted to Canada',
|
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://gem.cbc.ca/nadiyas-family-favourites/s01e01',
|
'url': 'https://gem.cbc.ca/nadiyas-family-favourites/s01e01',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
@ -631,38 +633,6 @@ class CBCGemIE(InfoExtractor):
|
||||||
return
|
return
|
||||||
self._claims_token = self.cache.load(self._NETRC_MACHINE, 'claims_token')
|
self._claims_token = self.cache.load(self._NETRC_MACHINE, 'claims_token')
|
||||||
|
|
||||||
def _find_secret_formats(self, formats, video_id):
|
|
||||||
""" Find a valid video url and convert it to the secret variant """
|
|
||||||
base_format = next((f for f in formats if f.get('vcodec') != 'none'), None)
|
|
||||||
if not base_format:
|
|
||||||
return
|
|
||||||
|
|
||||||
base_url = re.sub(r'(Manifest\(.*?),filter=[\w-]+(.*?\))', r'\1\2', base_format['url'])
|
|
||||||
url = re.sub(r'(Manifest\(.*?),format=[\w-]+(.*?\))', r'\1\2', base_url)
|
|
||||||
|
|
||||||
secret_xml = self._download_xml(url, video_id, note='Downloading secret XML', fatal=False)
|
|
||||||
if not isinstance(secret_xml, xml.etree.ElementTree.Element):
|
|
||||||
return
|
|
||||||
|
|
||||||
for child in secret_xml:
|
|
||||||
if child.attrib.get('Type') != 'video':
|
|
||||||
continue
|
|
||||||
for video_quality in child:
|
|
||||||
bitrate = int_or_none(video_quality.attrib.get('Bitrate'))
|
|
||||||
if not bitrate or 'Index' not in video_quality.attrib:
|
|
||||||
continue
|
|
||||||
height = int_or_none(video_quality.attrib.get('MaxHeight'))
|
|
||||||
|
|
||||||
yield {
|
|
||||||
**base_format,
|
|
||||||
'format_id': join_nonempty('sec', height),
|
|
||||||
# Note: \g<1> is necessary instead of \1 since bitrate is a number
|
|
||||||
'url': re.sub(r'(QualityLevels\()\d+(\))', fr'\g<1>{bitrate}\2', base_url),
|
|
||||||
'width': int_or_none(video_quality.attrib.get('MaxWidth')),
|
|
||||||
'tbr': bitrate / 1000.0,
|
|
||||||
'height': height,
|
|
||||||
}
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
video_info = self._download_json(
|
video_info = self._download_json(
|
||||||
|
@ -676,7 +646,6 @@ class CBCGemIE(InfoExtractor):
|
||||||
else:
|
else:
|
||||||
headers = {}
|
headers = {}
|
||||||
m3u8_info = self._download_json(video_info['playSession']['url'], video_id, headers=headers)
|
m3u8_info = self._download_json(video_info['playSession']['url'], video_id, headers=headers)
|
||||||
m3u8_url = m3u8_info.get('url')
|
|
||||||
|
|
||||||
if m3u8_info.get('errorCode') == 1:
|
if m3u8_info.get('errorCode') == 1:
|
||||||
self.raise_geo_restricted(countries=['CA'])
|
self.raise_geo_restricted(countries=['CA'])
|
||||||
|
@ -685,9 +654,9 @@ class CBCGemIE(InfoExtractor):
|
||||||
elif m3u8_info.get('errorCode') != 0:
|
elif m3u8_info.get('errorCode') != 0:
|
||||||
raise ExtractorError(f'{self.IE_NAME} said: {m3u8_info.get("errorCode")} - {m3u8_info.get("message")}')
|
raise ExtractorError(f'{self.IE_NAME} said: {m3u8_info.get("errorCode")} - {m3u8_info.get("message")}')
|
||||||
|
|
||||||
formats = self._extract_m3u8_formats(m3u8_url, video_id, m3u8_id='hls')
|
formats = self._extract_m3u8_formats(
|
||||||
|
m3u8_info['url'], video_id, 'mp4', m3u8_id='hls', query={'manifestType': ''})
|
||||||
self._remove_duplicate_formats(formats)
|
self._remove_duplicate_formats(formats)
|
||||||
formats.extend(self._find_secret_formats(formats, video_id))
|
|
||||||
|
|
||||||
for fmt in formats:
|
for fmt in formats:
|
||||||
if fmt.get('vcodec') == 'none':
|
if fmt.get('vcodec') == 'none':
|
||||||
|
@ -703,20 +672,21 @@ class CBCGemIE(InfoExtractor):
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': video_info['title'],
|
|
||||||
'description': video_info.get('description'),
|
|
||||||
'thumbnail': video_info.get('image'),
|
|
||||||
'series': video_info.get('series'),
|
|
||||||
'season_number': video_info.get('season'),
|
|
||||||
'season': f'Season {video_info.get("season")}',
|
|
||||||
'episode_number': video_info.get('episode'),
|
|
||||||
'episode': video_info.get('title'),
|
|
||||||
'episode_id': video_id,
|
'episode_id': video_id,
|
||||||
'duration': video_info.get('duration'),
|
|
||||||
'categories': [video_info.get('category')],
|
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'release_timestamp': video_info.get('airDate'),
|
**traverse_obj(video_info, {
|
||||||
'timestamp': video_info.get('availableDate'),
|
'title': ('title', {str}),
|
||||||
|
'episode': ('title', {str}),
|
||||||
|
'description': ('description', {str}),
|
||||||
|
'thumbnail': ('image', {url_or_none}),
|
||||||
|
'series': ('series', {str}),
|
||||||
|
'season_number': ('season', {int_or_none}),
|
||||||
|
'episode_number': ('episode', {int_or_none}),
|
||||||
|
'duration': ('duration', {int_or_none}),
|
||||||
|
'categories': ('category', {str}, all),
|
||||||
|
'release_timestamp': ('airDate', {int_or_none(scale=1000)}),
|
||||||
|
'timestamp': ('availableDate', {int_or_none(scale=1000)}),
|
||||||
|
}),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -1,113 +1,100 @@
|
||||||
import re
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from .. import traverse_obj
|
||||||
determine_ext,
|
from ..utils import determine_ext, int_or_none, parse_count, parse_duration, parse_iso8601, url_or_none
|
||||||
extract_attributes,
|
|
||||||
int_or_none,
|
|
||||||
str_to_int,
|
|
||||||
url_or_none,
|
|
||||||
urlencode_postdata,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class ManyVidsIE(InfoExtractor):
|
class ManyVidsIE(InfoExtractor):
|
||||||
_WORKING = False
|
_WORKING = True
|
||||||
_VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
|
_VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
|
||||||
_TESTS = [{
|
_TESTS = [
|
||||||
# preview video
|
{
|
||||||
'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
|
# Dead preview video
|
||||||
'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
|
'skip': True,
|
||||||
'info_dict': {
|
'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
|
||||||
'id': '133957',
|
'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
|
||||||
'ext': 'mp4',
|
'info_dict': {
|
||||||
'title': 'everthing about me (Preview)',
|
'id': '133957',
|
||||||
'uploader': 'ellyxxix',
|
'ext': 'mp4',
|
||||||
'view_count': int,
|
'title': 'everthing about me (Preview)',
|
||||||
'like_count': int,
|
'uploader': 'ellyxxix',
|
||||||
|
'view_count': int,
|
||||||
|
'like_count': int,
|
||||||
|
},
|
||||||
},
|
},
|
||||||
}, {
|
{
|
||||||
# full video
|
# preview video
|
||||||
'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
|
'url': 'https://www.manyvids.com/Video/530341/mv-tips-tricks',
|
||||||
'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
|
'md5': '738dc723f7735ee9602f7ea352a6d058',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '935718',
|
'id': '530341',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'MY FACE REVEAL',
|
'title': 'MV Tips & Tricks (Preview)',
|
||||||
'description': 'md5:ec5901d41808b3746fed90face161612',
|
'description': 'md5:c3bae98c0f9453237c28b0f8795d9f83',
|
||||||
'uploader': 'Sarah Calanthe',
|
'thumbnail': 'https://cdn5.manyvids.com/php_uploads/video_images/DestinyDiaz/thumbs/thumb_Hs26ATOO7fcZaI9sx3XT_screenshot_001.jpg',
|
||||||
'view_count': int,
|
'uploader': 'DestinyDiaz',
|
||||||
'like_count': int,
|
'view_count': int,
|
||||||
|
'like_count': int,
|
||||||
|
'release_timestamp': 1508419904,
|
||||||
|
'tags': ['AdultSchool', 'BBW', 'SFW', 'TeacherFetish'],
|
||||||
|
'release_date': '20171019',
|
||||||
|
'duration': 3167.0,
|
||||||
|
},
|
||||||
},
|
},
|
||||||
}]
|
{
|
||||||
|
# full video
|
||||||
|
'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
|
||||||
|
'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '935718',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'MY FACE REVEAL',
|
||||||
|
'description': 'md5:ec5901d41808b3746fed90face161612',
|
||||||
|
'thumbnail': 'https://ods.manyvids.com/1001061960/3aa5397f2a723ec4597e344df66ab845/screenshots/thumbs/custom_1_180_5be09c1dcce03.jpg',
|
||||||
|
'uploader': 'Sarah Calanthe',
|
||||||
|
'view_count': int,
|
||||||
|
'like_count': int,
|
||||||
|
'release_date': '20181110',
|
||||||
|
'tags': ['EyeContact', 'Interviews', 'MaskFetish', 'MouthFetish', 'Redhead'],
|
||||||
|
'release_timestamp': 1541851200,
|
||||||
|
'duration': 224.0,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
real_url = f'https://www.manyvids.com/video/{video_id}/gtm.js'
|
info = traverse_obj(
|
||||||
try:
|
self._download_json(f'https://www.manyvids.com/bff/store/video/{video_id}', video_id),
|
||||||
webpage = self._download_webpage(real_url, video_id)
|
('data', {dict})) or {}
|
||||||
except Exception:
|
|
||||||
# probably useless fallback
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
|
|
||||||
info = self._search_regex(
|
video_urls = traverse_obj(
|
||||||
r'''(<div\b[^>]*\bid\s*=\s*(['"])pageMetaDetails\2[^>]*>)''',
|
self._download_json(f'https://www.manyvids.com/bff/store/video/{video_id}/private', video_id),
|
||||||
webpage, 'meta details', default='')
|
('data', {dict})) or {}
|
||||||
info = extract_attributes(info)
|
|
||||||
|
|
||||||
player = self._search_regex(
|
|
||||||
r'''(<div\b[^>]*\bid\s*=\s*(['"])rmpPlayerStream\2[^>]*>)''',
|
|
||||||
webpage, 'player details', default='')
|
|
||||||
player = extract_attributes(player)
|
|
||||||
|
|
||||||
video_urls_and_ids = (
|
video_urls_and_ids = (
|
||||||
(info.get('data-meta-video'), 'video'),
|
(traverse_obj(video_urls, ('teaser', 'filepath')), 'preview'),
|
||||||
(player.get('data-video-transcoded'), 'transcoded'),
|
(video_urls.get('transcodedFilepath'), 'transcoded'),
|
||||||
(player.get('data-video-filepath'), 'filepath'),
|
(video_urls.get('filepath'), 'filepath'),
|
||||||
(self._og_search_video_url(webpage, secure=False, default=None), 'og_video'),
|
|
||||||
)
|
)
|
||||||
|
|
||||||
def txt_or_none(s, default=None):
|
title = info.get('title')
|
||||||
return (s.strip() or default) if isinstance(s, str) else default
|
uploader = traverse_obj(info, ('model', 'displayName'))
|
||||||
|
description = info.get('description')
|
||||||
|
likes = parse_count(info.get('likes'))
|
||||||
|
views = parse_count(info.get('views'))
|
||||||
|
thumbnail = url_or_none(info.get('screenshot')) or url_or_none(info.get('thumbnail'))
|
||||||
|
release_timestamp = parse_iso8601(info.get('launchDate'))
|
||||||
|
duration = parse_duration(info.get('videoDuration'))
|
||||||
|
tags = [t.get('label') for t in info.get('tagList')]
|
||||||
|
|
||||||
uploader = txt_or_none(info.get('data-meta-author'))
|
# If the video formats JSON only contains a teaser object, then it is a preview
|
||||||
|
if video_urls.get('teaser') and not video_urls.get('filepath'):
|
||||||
def mung_title(s):
|
|
||||||
if uploader:
|
|
||||||
s = re.sub(rf'^\s*{re.escape(uploader)}\s+[|-]', '', s)
|
|
||||||
return txt_or_none(s)
|
|
||||||
|
|
||||||
title = (
|
|
||||||
mung_title(info.get('data-meta-title'))
|
|
||||||
or self._html_search_regex(
|
|
||||||
(r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
|
|
||||||
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
|
|
||||||
webpage, 'title', default=None)
|
|
||||||
or self._html_search_meta(
|
|
||||||
'twitter:title', webpage, 'title', fatal=True))
|
|
||||||
|
|
||||||
title = re.sub(r'\s*[|-]\s+ManyVids\s*$', '', title) or title
|
|
||||||
|
|
||||||
if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
|
|
||||||
title += ' (Preview)'
|
title += ' (Preview)'
|
||||||
|
self.report_warning(
|
||||||
mv_token = self._search_regex(
|
f'Only extracting preview. Video may be paid or subscription only. {self._login_hint()}')
|
||||||
r'data-mvtoken=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
|
|
||||||
'mv token', default=None, group='value')
|
|
||||||
|
|
||||||
if mv_token:
|
|
||||||
# Sets some cookies
|
|
||||||
self._download_webpage(
|
|
||||||
'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
|
|
||||||
video_id, note='Setting format cookies', fatal=False,
|
|
||||||
data=urlencode_postdata({
|
|
||||||
'mvtoken': mv_token,
|
|
||||||
'vid': video_id,
|
|
||||||
}), headers={
|
|
||||||
'Referer': url,
|
|
||||||
'X-Requested-With': 'XMLHttpRequest',
|
|
||||||
})
|
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
for v_url, fmt in video_urls_and_ids:
|
for v_url, fmt in video_urls_and_ids:
|
||||||
|
@ -130,33 +117,21 @@ class ManyVidsIE(InfoExtractor):
|
||||||
if f.get('height') is None:
|
if f.get('height') is None:
|
||||||
f['height'] = int_or_none(
|
f['height'] = int_or_none(
|
||||||
self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
|
self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
|
||||||
if '/preview/' in f['url']:
|
if 'preview' in f['format_id']:
|
||||||
f['format_id'] = '_'.join(filter(None, (f.get('format_id'), 'preview')))
|
|
||||||
f['preference'] = -10
|
f['preference'] = -10
|
||||||
if 'transcoded' in f['format_id']:
|
if 'transcoded' in f['format_id']:
|
||||||
f['preference'] = f.get('preference', -1) - 1
|
f['preference'] = f.get('preference', -1) - 1
|
||||||
|
|
||||||
def get_likes():
|
|
||||||
likes = self._search_regex(
|
|
||||||
rf'''(<a\b[^>]*\bdata-id\s*=\s*(['"]){video_id}\2[^>]*>)''',
|
|
||||||
webpage, 'likes', default='')
|
|
||||||
likes = extract_attributes(likes)
|
|
||||||
return int_or_none(likes.get('data-likes'))
|
|
||||||
|
|
||||||
def get_views():
|
|
||||||
return str_to_int(self._html_search_regex(
|
|
||||||
r'''(?s)<span\b[^>]*\bclass\s*=["']views-wrapper\b[^>]+>.+?<span\b[^>]+>\s*(\d[\d,.]*)\s*</span>''',
|
|
||||||
webpage, 'view count', default=None))
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'description': txt_or_none(info.get('data-meta-description')),
|
'description': description,
|
||||||
'uploader': txt_or_none(info.get('data-meta-author')),
|
'uploader': uploader,
|
||||||
'thumbnail': (
|
'thumbnail': thumbnail,
|
||||||
url_or_none(info.get('data-meta-image'))
|
'view_count': views,
|
||||||
or url_or_none(player.get('data-video-screenshot'))),
|
'like_count': likes,
|
||||||
'view_count': get_views(),
|
'release_timestamp': release_timestamp,
|
||||||
'like_count': get_likes(),
|
'duration': duration,
|
||||||
|
'tags': tags,
|
||||||
}
|
}
|
||||||
|
|
|
@ -1,14 +1,13 @@
|
||||||
from .telecinco import TelecincoIE
|
from .telecinco import TelecincoBaseIE
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
int_or_none,
|
int_or_none,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
|
class MiTeleIE(TelecincoBaseIE):
|
||||||
IE_DESC = 'mitele.es'
|
IE_DESC = 'mitele.es'
|
||||||
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
|
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
|
'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
|
@ -27,6 +26,7 @@ class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
|
||||||
'timestamp': 1471209401,
|
'timestamp': 1471209401,
|
||||||
'upload_date': '20160814',
|
'upload_date': '20160814',
|
||||||
},
|
},
|
||||||
|
'skip': 'HTTP Error 404 Not Found',
|
||||||
}, {
|
}, {
|
||||||
# no explicit title
|
# no explicit title
|
||||||
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
|
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
|
||||||
|
@ -49,6 +49,26 @@ class MiTeleIE(TelecincoIE): # XXX: Do not subclass from concrete IE
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
|
'skip': 'HTTP Error 404 Not Found',
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.mitele.es/programas-tv/horizonte/temporada-5/programa-171-40_013480051/player/',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '7adbe22e-cd41-4787-afa4-36f3da7c2c6f',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Horizonte Temporada 5 Programa 171',
|
||||||
|
'description': 'md5:97f1fb712c5ac27e5693a8b3c5c0c6e3',
|
||||||
|
'episode': 'Las Zonas de Bajas Emisiones, a debate',
|
||||||
|
'episode_number': 171,
|
||||||
|
'season': 'Season 5',
|
||||||
|
'season_number': 5,
|
||||||
|
'series': 'Horizonte',
|
||||||
|
'duration': 7012,
|
||||||
|
'upload_date': '20240927',
|
||||||
|
'timestamp': 1727416450,
|
||||||
|
'thumbnail': 'https://album.mediaset.es/eimg/2024/09/27/horizonte-171_9f02.jpg',
|
||||||
|
'age_limit': 12,
|
||||||
|
},
|
||||||
|
'params': {'geo_bypass_country': 'ES'},
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
|
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
|
|
@ -2,15 +2,69 @@ import json
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..networking.exceptions import HTTPError
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
|
ExtractorError,
|
||||||
clean_html,
|
clean_html,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
|
join_nonempty,
|
||||||
str_or_none,
|
str_or_none,
|
||||||
try_get,
|
traverse_obj,
|
||||||
|
update_url,
|
||||||
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class TelecincoIE(InfoExtractor):
|
class TelecincoBaseIE(InfoExtractor):
|
||||||
|
def _parse_content(self, content, url):
|
||||||
|
video_id = content['dataMediaId']
|
||||||
|
config = self._download_json(
|
||||||
|
content['dataConfig'], video_id, 'Downloading config JSON')
|
||||||
|
services = config['services']
|
||||||
|
caronte = self._download_json(services['caronte'], video_id)
|
||||||
|
if traverse_obj(caronte, ('dls', 0, 'drm', {bool})):
|
||||||
|
self.report_drm(video_id)
|
||||||
|
|
||||||
|
stream = caronte['dls'][0]['stream']
|
||||||
|
headers = {
|
||||||
|
'Referer': url,
|
||||||
|
'Origin': re.match(r'https?://[^/]+', url).group(0),
|
||||||
|
}
|
||||||
|
geo_headers = {**headers, **self.geo_verification_headers()}
|
||||||
|
|
||||||
|
try:
|
||||||
|
cdn = self._download_json(
|
||||||
|
caronte['cerbero'], video_id, data=json.dumps({
|
||||||
|
'bbx': caronte['bbx'],
|
||||||
|
'gbx': self._download_json(services['gbx'], video_id)['gbx'],
|
||||||
|
}).encode(), headers={
|
||||||
|
'Content-Type': 'application/json',
|
||||||
|
**geo_headers,
|
||||||
|
})['tokens']['1']['cdn']
|
||||||
|
except ExtractorError as error:
|
||||||
|
if isinstance(error.cause, HTTPError) and error.cause.status == 403:
|
||||||
|
error_code = traverse_obj(
|
||||||
|
self._webpage_read_content(error.cause.response, caronte['cerbero'], video_id, fatal=False),
|
||||||
|
({json.loads}, 'code', {int}))
|
||||||
|
if error_code == 4038:
|
||||||
|
self.raise_geo_restricted(countries=['ES'])
|
||||||
|
raise
|
||||||
|
|
||||||
|
formats = self._extract_m3u8_formats(
|
||||||
|
update_url(stream, query=cdn), video_id, 'mp4', m3u8_id='hls', headers=geo_headers)
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'title': traverse_obj(config, ('info', 'title', {str})),
|
||||||
|
'formats': formats,
|
||||||
|
'thumbnail': (traverse_obj(content, ('dataPoster', {url_or_none}))
|
||||||
|
or traverse_obj(config, 'poster', 'imageUrl', expected_type=url_or_none)),
|
||||||
|
'duration': traverse_obj(content, ('dataDuration', {int_or_none})),
|
||||||
|
'http_headers': headers,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
class TelecincoIE(TelecincoBaseIE):
|
||||||
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
|
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
|
_VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
|
||||||
|
|
||||||
|
@ -30,6 +84,7 @@ class TelecincoIE(InfoExtractor):
|
||||||
'duration': 662,
|
'duration': 662,
|
||||||
},
|
},
|
||||||
}],
|
}],
|
||||||
|
'skip': 'HTTP Error 410 Gone',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
|
'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
|
||||||
'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
|
'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
|
||||||
|
@ -40,23 +95,24 @@ class TelecincoIE(InfoExtractor):
|
||||||
'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
|
'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
|
||||||
'duration': 79,
|
'duration': 79,
|
||||||
},
|
},
|
||||||
|
'skip': 'Redirects to main page',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
|
'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
|
||||||
'md5': 'eddb50291df704ce23c74821b995bcac',
|
'md5': '5ce057f43f30b634fbaf0f18c71a140a',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'aywerkD2Sv1vGNqq9b85Q2',
|
'id': 'aywerkD2Sv1vGNqq9b85Q2',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '#DOYLACARA. Con la trata no hay trato',
|
'title': '#DOYLACARA. Con la trata no hay trato',
|
||||||
'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
|
|
||||||
'duration': 50,
|
'duration': 50,
|
||||||
|
'thumbnail': 'https://album.mediaset.es/eimg/2017/11/02/1tlQLO5Q3mtKT24f3EaC24.jpg',
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
# video in opening's content
|
# video in opening's content
|
||||||
'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
|
'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2907195140',
|
'id': '1691427',
|
||||||
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
|
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
|
||||||
'description': 'md5:73f340a7320143d37ab895375b2bf13a',
|
'description': r're:Fiorella, la sobrina de Edmundo Arrocet, concedió .{727}',
|
||||||
},
|
},
|
||||||
'playlist': [{
|
'playlist': [{
|
||||||
'md5': 'adb28c37238b675dad0f042292f209a7',
|
'md5': 'adb28c37238b675dad0f042292f209a7',
|
||||||
|
@ -65,6 +121,7 @@ class TelecincoIE(InfoExtractor):
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
|
'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
|
||||||
'duration': 1015,
|
'duration': 1015,
|
||||||
|
'thumbnail': 'https://album.mediaset.es/eimg/2020/02/29/5opaC37lUhKlZ7FoDhiVC.jpg',
|
||||||
},
|
},
|
||||||
}],
|
}],
|
||||||
'params': {
|
'params': {
|
||||||
|
@ -81,66 +138,29 @@ class TelecincoIE(InfoExtractor):
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _parse_content(self, content, url):
|
|
||||||
video_id = content['dataMediaId']
|
|
||||||
config = self._download_json(
|
|
||||||
content['dataConfig'], video_id, 'Downloading config JSON')
|
|
||||||
title = config['info']['title']
|
|
||||||
services = config['services']
|
|
||||||
caronte = self._download_json(services['caronte'], video_id)
|
|
||||||
stream = caronte['dls'][0]['stream']
|
|
||||||
headers = self.geo_verification_headers()
|
|
||||||
headers.update({
|
|
||||||
'Content-Type': 'application/json;charset=UTF-8',
|
|
||||||
'Origin': re.match(r'https?://[^/]+', url).group(0),
|
|
||||||
})
|
|
||||||
cdn = self._download_json(
|
|
||||||
caronte['cerbero'], video_id, data=json.dumps({
|
|
||||||
'bbx': caronte['bbx'],
|
|
||||||
'gbx': self._download_json(services['gbx'], video_id)['gbx'],
|
|
||||||
}).encode(), headers=headers)['tokens']['1']['cdn']
|
|
||||||
formats = self._extract_m3u8_formats(
|
|
||||||
stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
|
|
||||||
|
|
||||||
return {
|
|
||||||
'id': video_id,
|
|
||||||
'title': title,
|
|
||||||
'formats': formats,
|
|
||||||
'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
|
|
||||||
'duration': int_or_none(content.get('dataDuration')),
|
|
||||||
}
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
display_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
article = self._parse_json(self._search_regex(
|
article = self._search_json(
|
||||||
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})',
|
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
|
||||||
webpage, 'article'), display_id)['article']
|
webpage, 'article', display_id)['article']
|
||||||
title = article.get('title')
|
description = traverse_obj(article, ('leadParagraph', {clean_html}, filter))
|
||||||
description = clean_html(article.get('leadParagraph')) or ''
|
|
||||||
if article.get('editorialType') != 'VID':
|
if article.get('editorialType') != 'VID':
|
||||||
entries = []
|
entries = []
|
||||||
body = [article.get('opening')]
|
|
||||||
body.extend(try_get(article, lambda x: x['body'], list) or [])
|
for p in traverse_obj(article, ((('opening', all), 'body'), lambda _, v: v['content'])):
|
||||||
for p in body:
|
content = p['content']
|
||||||
if not isinstance(p, dict):
|
|
||||||
continue
|
|
||||||
content = p.get('content')
|
|
||||||
if not content:
|
|
||||||
continue
|
|
||||||
type_ = p.get('type')
|
type_ = p.get('type')
|
||||||
if type_ == 'paragraph':
|
if type_ == 'paragraph' and isinstance(content, str):
|
||||||
content_str = str_or_none(content)
|
description = join_nonempty(description, content, delim='')
|
||||||
if content_str:
|
elif type_ == 'video' and isinstance(content, dict):
|
||||||
description += content_str
|
|
||||||
continue
|
|
||||||
if type_ == 'video' and isinstance(content, dict):
|
|
||||||
entries.append(self._parse_content(content, url))
|
entries.append(self._parse_content(content, url))
|
||||||
|
|
||||||
return self.playlist_result(
|
return self.playlist_result(
|
||||||
entries, str_or_none(article.get('id')), title, description)
|
entries, str_or_none(article.get('id')),
|
||||||
content = article['opening']['content']
|
traverse_obj(article, ('title', {str})), clean_html(description))
|
||||||
info = self._parse_content(content, url)
|
|
||||||
info.update({
|
info = self._parse_content(article['opening']['content'], url)
|
||||||
'description': description,
|
info['description'] = description
|
||||||
})
|
|
||||||
return info
|
return info
|
||||||
|
|
|
@ -114,6 +114,7 @@ INNERTUBE_CLIENTS = {
|
||||||
},
|
},
|
||||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
|
||||||
},
|
},
|
||||||
|
# This client now requires sign-in for every video
|
||||||
'web_creator': {
|
'web_creator': {
|
||||||
'INNERTUBE_CONTEXT': {
|
'INNERTUBE_CONTEXT': {
|
||||||
'client': {
|
'client': {
|
||||||
|
@ -153,6 +154,7 @@ INNERTUBE_CLIENTS = {
|
||||||
'REQUIRE_JS_PLAYER': False,
|
'REQUIRE_JS_PLAYER': False,
|
||||||
'REQUIRE_PO_TOKEN': True,
|
'REQUIRE_PO_TOKEN': True,
|
||||||
},
|
},
|
||||||
|
# This client now requires sign-in for every video
|
||||||
'android_creator': {
|
'android_creator': {
|
||||||
'INNERTUBE_CONTEXT': {
|
'INNERTUBE_CONTEXT': {
|
||||||
'client': {
|
'client': {
|
||||||
|
@ -200,21 +202,6 @@ INNERTUBE_CLIENTS = {
|
||||||
'REQUIRE_JS_PLAYER': False,
|
'REQUIRE_JS_PLAYER': False,
|
||||||
'PLAYER_PARAMS': '2AMB',
|
'PLAYER_PARAMS': '2AMB',
|
||||||
},
|
},
|
||||||
# This client only has legacy formats and storyboards
|
|
||||||
'android_producer': {
|
|
||||||
'INNERTUBE_CONTEXT': {
|
|
||||||
'client': {
|
|
||||||
'clientName': 'ANDROID_PRODUCER',
|
|
||||||
'clientVersion': '0.111.1',
|
|
||||||
'androidSdkVersion': 30,
|
|
||||||
'userAgent': 'com.google.android.apps.youtube.producer/0.111.1 (Linux; U; Android 11) gzip',
|
|
||||||
'osName': 'Android',
|
|
||||||
'osVersion': '11',
|
|
||||||
},
|
|
||||||
},
|
|
||||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 91,
|
|
||||||
'REQUIRE_JS_PLAYER': False,
|
|
||||||
},
|
|
||||||
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
|
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
|
||||||
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
|
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
|
||||||
'ios': {
|
'ios': {
|
||||||
|
@ -247,6 +234,7 @@ INNERTUBE_CLIENTS = {
|
||||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
|
||||||
'REQUIRE_JS_PLAYER': False,
|
'REQUIRE_JS_PLAYER': False,
|
||||||
},
|
},
|
||||||
|
# This client now requires sign-in for every video
|
||||||
'ios_creator': {
|
'ios_creator': {
|
||||||
'INNERTUBE_CONTEXT': {
|
'INNERTUBE_CONTEXT': {
|
||||||
'client': {
|
'client': {
|
||||||
|
@ -282,8 +270,9 @@ INNERTUBE_CLIENTS = {
|
||||||
},
|
},
|
||||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
|
||||||
},
|
},
|
||||||
# This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
|
# This client now requires sign-in for every video
|
||||||
# See: https://github.com/zerodytrash/YouTube-Internal-Clients
|
# It was previously an age-gate workaround for videos that were `playable_in_embed`
|
||||||
|
# It may still be useful if signed into an EU account that is not age-verified
|
||||||
'tv_embedded': {
|
'tv_embedded': {
|
||||||
'INNERTUBE_CONTEXT': {
|
'INNERTUBE_CONTEXT': {
|
||||||
'client': {
|
'client': {
|
||||||
|
@ -1525,6 +1514,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
'heatmap': 'count:100',
|
'heatmap': 'count:100',
|
||||||
'timestamp': 1401991663,
|
'timestamp': 1401991663,
|
||||||
},
|
},
|
||||||
|
'skip': 'Age-restricted; requires authentication',
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'note': 'Age-gate video with embed allowed in public site',
|
'note': 'Age-gate video with embed allowed in public site',
|
||||||
|
@ -1555,6 +1545,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
'comment_count': int,
|
'comment_count': int,
|
||||||
'channel_is_verified': True,
|
'channel_is_verified': True,
|
||||||
},
|
},
|
||||||
|
'skip': 'Age-restricted; requires authentication',
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'note': 'Age-gate video embedable only with clientScreen=EMBED',
|
'note': 'Age-gate video embedable only with clientScreen=EMBED',
|
||||||
|
@ -1585,6 +1576,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
'uploader_id': '@ProjektMelody',
|
'uploader_id': '@ProjektMelody',
|
||||||
'timestamp': 1577508724,
|
'timestamp': 1577508724,
|
||||||
},
|
},
|
||||||
|
'skip': 'Age-restricted; requires authentication',
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'note': 'Non-Agegated non-embeddable video',
|
'note': 'Non-Agegated non-embeddable video',
|
||||||
|
@ -2356,6 +2348,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
'channel_is_verified': True,
|
'channel_is_verified': True,
|
||||||
'timestamp': 1405513526,
|
'timestamp': 1405513526,
|
||||||
},
|
},
|
||||||
|
'skip': 'Age-restricted; requires authentication',
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
# restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
|
# restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
|
||||||
|
@ -2726,6 +2719,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
'timestamp': 1577508724,
|
'timestamp': 1577508724,
|
||||||
},
|
},
|
||||||
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
|
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
|
||||||
|
'skip': 'Age-restricted; requires authentication',
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'url': 'https://www.youtube.com/live/qVv6vCqciTM',
|
'url': 'https://www.youtube.com/live/qVv6vCqciTM',
|
||||||
|
@ -3953,26 +3947,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
else:
|
else:
|
||||||
prs.append(pr)
|
prs.append(pr)
|
||||||
|
|
||||||
# tv_embedded can work around age-gate and age-verification IF the video is embeddable
|
|
||||||
if self._is_agegated(pr) and variant != 'tv_embedded':
|
|
||||||
append_client(f'tv_embedded.{base_client}')
|
|
||||||
|
|
||||||
# Unauthenticated users will only get tv_embedded client formats if age-gated
|
|
||||||
if self._is_agegated(pr) and not self.is_authenticated:
|
|
||||||
self.to_screen(
|
|
||||||
f'{video_id}: This video is age-restricted; some formats may be missing '
|
|
||||||
f'without authentication. {self._login_hint()}', only_once=True)
|
|
||||||
|
|
||||||
# EU countries require age-verification for accounts to access age-restricted videos
|
# EU countries require age-verification for accounts to access age-restricted videos
|
||||||
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
|
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
|
||||||
# If embedding is disabled for the video, _is_unplayable() will be truthy for tv_embedded
|
if self.is_authenticated and self._is_agegated(pr):
|
||||||
embedding_is_disabled = variant == 'tv_embedded' and self._is_unplayable(pr)
|
|
||||||
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
|
|
||||||
self.to_screen(
|
self.to_screen(
|
||||||
f'{video_id}: This video is age-restricted and YouTube is requiring '
|
f'{video_id}: This video is age-restricted and YouTube is requiring '
|
||||||
'account age-verification; some formats may be missing', only_once=True)
|
'account age-verification; some formats may be missing', only_once=True)
|
||||||
# web_creator and mediaconnect can work around the age-verification requirement
|
# web_creator and mediaconnect can work around the age-verification requirement
|
||||||
# _producer, _testsuite, & _vr variants can also work around age-verification
|
# _testsuite & _vr variants can also work around age-verification
|
||||||
|
# tv_embedded may(?) still work around age-verification if the video is embeddable
|
||||||
append_client('web_creator', 'mediaconnect')
|
append_client('web_creator', 'mediaconnect')
|
||||||
|
|
||||||
prs.extend(deprioritized_prs)
|
prs.extend(deprioritized_prs)
|
||||||
|
|
Loading…
Reference in New Issue
Block a user